python 图像去重 删除重复 相似的图像

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import cv2
from skimage.metrics import structural_similarity

def get_filelist(filepath, filelist):
    if os.path.isfile(filepath):
        if filepath.endswith('.jpg'):
            filelist.append(filepath)
    elif os.path.isdir(filepath):
        for path in os.listdir(filepath):
            new_path = os.path.join(filepath, path)
            get_filelist(new_path, filelist)
    return filelist

def delete_similar_img(filelist, index=0):
    if index == len(filelist):
        return
    else:
        file0 = filelist[index]
        if os.path.exists(file0):
            img0 = cv2.imread(file0)
            for idx in range(index + 1, len(filelist)):
                file1 = filelist[idx]
                if not os.path.exists(file1):
                    continue
                img1 = cv2.imread(file1)
                if img0.size == img1.size:
                    print(f'{filelist[index]} 与 {filelist[idx]} 尺寸一致')
                    ssim = structural_similarity(img0, img1, multichannel=True)
                    if ssim > 0.9:
                        os.remove(file1)
                else:
                    print(f'{filelist[index]} 与 {filelist[idx]} 尺寸不一致')
        index += 1
        delete_similar_img(filelist, index)

if __name__ == '__main__':
    testPath = r'E:\test1'
    fileList = []
    imgList = get_filelist(testPath, fileList)
    delete_similar_img(imgList)

如果出现如下报错

ValueError: win_size exceeds image extent. Either ensure that your images are at least 7x7; or pass win_size explicitly in the function call, with an odd value less than or equal to the smaller side of your images. If your images are multichannel (with color channels), set channel_axis to the axis number corresponding to the channels.
可将代码修改为

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import cv2
from skimage.metrics import structural_similarity


def get_filelist(filepath, filelist):
    if os.path.isfile(filepath):
        if filepath.endswith('.jpg'):
            filelist.append(filepath)
    elif os.path.isdir(filepath):
        for path in os.listdir(filepath):
            new_path = os.path.join(filepath, path)
            get_filelist(new_path, filelist)
    return filelist


def delete_similar_img(filelist, index=0):
    if index == len(filelist):
        return
    else:
        file0 = filelist[index]
        if os.path.exists(file0):
            img0 = cv2.imread(file0)
            for idx in range(index + 1, len(filelist)):
                file1 = filelist[idx]
                if not os.path.exists(file1):
                    continue
                img1 = cv2.imread(file1)
                if img0.size == img1.size:
                    print(f'{filelist[index]} 与 {filelist[idx]} 尺寸一致')
                    # ssim = structural_similarity(img0, img1, multichannel=True)
                    ssim = structural_similarity(img0, img1, channel_axis=2)
                    if ssim > 0.9:
                        os.remove(file1)
                else:
                    print(f'{filelist[index]} 与 {filelist[idx]} 尺寸不一致')
        index += 1
        delete_similar_img(filelist, index)


if __name__ == '__main__':
    testPath = r'D:\Work\TestDir'
    fileList = []
    imgList = get_filelist(testPath, fileList)
    print(imgList)
    delete_similar_img(imgList)

参考链接：win_size exceeds image extent. Either ensure that your images are at least 7x7； or pass win_size ex_valueerror: win_size exceeds image extent. either -CSDN博客